We're updating the leaderboard

The full-benchmark results are temporarily offline while we update them. They will be back soon.

The public 80-question release and its leaderboard are still on the MoveBench dataset page.

榜单正在更新，全量结果暂时下线，稍后恢复。80 题公开版本及其榜单请见 MoveBench 数据集页面。